© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 31007
    Prev
    Next
    INDEX
    Explanations

    the name "Ari"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.19
    1.1%
    71
    +0.15
    0.9%
    423
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.19
    0.01
    423
    +0.15
    0.01
    443
    +0.13
    0.01
    Negative Logits
     entire
    -1.78
     latter
    -1.56
     eastern
    -1.52
    ization
    -1.50
    deal
    -1.47
     previous
    -1.47
    heres
    -1.47
    shore
    -1.46
     descent
    -1.46
     favor
    -1.46
    POSITIVE LOGITS
    fried
    1.84
    ilee
    1.72
    umbered
    1.66
    witz
    1.64
    ailable
    1.61
    igent
    1.52
    uelle
    1.50
    leen
    1.50
    idity
    1.49
     handed
    1.48
    Activations Density 0.010%

    No Known Activations